Borrowing it
Nothing to install: this file belongs to sushiHex/hardline-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sushiHex/hardline-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/sushiHex/hardline-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sushihex/hardline-mcp/claude-md)<a href="https://agentmods.dev/instructions/sushihex/hardline-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sushihex/hardline-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/sushihex/hardline-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sushihex/hardline-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01624 | $0.01624 |
| Opus 5 | $0.00812 | $0.00812 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
hardline-mcp CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
last. `subprocess.run(text=True)` decodes as cp1252; `print()` encodes as How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hardline-mcp — working notes
The README explains what this is. This file is for working on it: the conventions, the gotchas that cost real time, and the rules the code already follows so new code follows them too.
The deployment this code actually lives in
Nearly every design decision here only makes sense against these three facts.
~20 hardline processes run at once, against one SQLite file. Each agent session spawns its own server over stdio. There is no coordinator.
It is an editable install. A process runs whatever the working tree said when it spawned — forever. So several different revisions of this code run against the same store simultaneously and indefinitely, and nothing restarts them together. A schema change is a change to a store that older code is still reading and writing.
The store is real. It holds hundreds of live messages and a jobs table. It is not a scratch database.
Three rules the code follows
New code should follow them too; several bugs came from breaking one.
Liveness is derived, never stored. A process that crashes cannot write "I
died", so the only true answer is to ask the OS at read time. That is why
jobs.lost and session liveness are both resolved on read and cost nothing
until somebody asks. No heartbeat thread, no TTL, no reaper.
A pid is not an identity. A pid is reused once its process exits, so every
durable record pairs it with a creation-time token (procid.process_key) and
compares before acting. Killing or trusting on a bare pid means killing or
trusting a stranger.
Absence is not evidence. The registry cannot see every consumer — a process on older code never registers, one whose announcement failed is absent, one behind an unanswerable probe looks gone. So absence from it never grants ownership of a lane. A claim needs positive evidence that nobody is there.
Related: liveness has three states, not two. UNKNOWN means the probe
could not answer, which is not death. Reads are optimistic about it; deletion
requires certainty.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +4 lines · +56 tokens per session 05b95beb9fec
- 2d ago First seen · 142 lines · 1,568 tokens per session scan A 3ce26c89d460
hardline-mcp CLAUDE.md is an instructions file published in the GitHub repository sushiHex/hardline-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 1,624 tokens to every session, about $0.0081 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).